Plugins

Ambient fullscreen status grid for DeepSeek Harness sessions with token/rate graphs, plus ntfy push and alarm notifications when a turn ends, errors, or waits for approval.

Two-way Feishu (Lark) chat bridge for DeepSeek Harness over the official WebSocket long connection: messages route to the bound workspace's latest session and replies return automatically; bot credentials and workspace routing are configurable from the settings page.

Exports metadata-only DSH turn, model, tool, approval, retry, and error events to Tuning Engines for governed traces, policy evaluation, cost analysis, and Work Session review, with a disk-backed retry queue.

Event-sourced cross-session work ledger: register, track and settle tasks with full audit history, kanban export, and a board digest injected into every model turn.

Document workshop skill pack: four pure-prompt Agent Skills that turn a codebase into READMEs, PR descriptions, changelogs and code reviews, installed into dsh via a dsh.bundle plugin row.

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.

Turn any SVG logo into a motion video inside DSH: an `animate_svg` tool renders a transparent 30fps assembly animation (parts fly in, or the whole mark settles) and synthesizes an MP4 with ffmpeg.

Turns markdown into a WeChat Official Account (微信公众号) draft: inlines every CSS rule onto its element because the editor discards `<style>` blocks and class names, uploads each local image through WeChat's own endpoint so it is not filtered out, and creates the draft; it never broadcasts.

LLM-driven remember/forget memory: after each turn a model decides what to keep (MemoryDirector), injects relevant memories before each step, dedups, and persists cross-session.

Clippy is back and this time he can actually help. An office assistant pet that reacts to real agent state, jumps when the turn completes, and opens a classic "illegal operation" dialog when a turn fails.

Fail-closed per-turn step, tool-call, and provider-token budgets for DeepSeek Harness

DeepSeek wallet-balance readout at the sidebar foot: card icon + amount, status-tinted, refreshed on turn end and on click

Brave Search API-backed search provider for the DeepSeek Harness web capability seam (ctx.web). One search is one HTTP request - no model turn.

Local AI code-review gate: review a workspace/branch/commit diff via the managed ocr.js, returning structured findings with token stats; gate mode fails on findings.